© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 59480
    Prev
    Next
    INDEX
    Explanations

    date and status information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ']['
    -1.70
    ;&#
    -1.63
    ”。
    -1.61
    }$.
    -1.59
    ]$.
    -1.57
    '].
    -1.52
    ”,
    -1.51
    Prensa
    -1.49
     had
    -1.47
    %">
    -1.47
    POSITIVE LOGITS
     Особенно
    1.43
     associée
    1.42
     Zustimmung
    1.35
     geralmente
    1.34
     juntamente
    1.32
    jenigen
    1.30
     asociado
    1.29
     particolarmente
    1.29
     schnelle
    1.28
     comienzan
    1.27
    Activations Density 0.008%

    No Known Activations